Analysis of Application Examples of Differential Privacy in Deep Learning

Artificial Intelligence has been widely applied today, and the subsequent privacy leakage problems have also been paid attention to. Attacks such as model inference attacks on deep neural networks can easily extract user information from neural networks. Therefore, it is necessary to protect privacy...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhidong Shen, Ting Zhong
Formato:	article
Lenguaje:	EN
Publicado:	Hindawi Limited 2021
Materias:	Computer applications to medicine. Medical informatics R858-859.7 Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
Acceso en línea:	https://doaj.org/article/a8167e7c4ee64b5785d00ee332a31e25
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a8167e7c4ee64b5785d00ee332a31e25
record_format	dspace
spelling	oai:doaj.org-article:a8167e7c4ee64b5785d00ee332a31e252021-11-08T02:37:08ZAnalysis of Application Examples of Differential Privacy in Deep Learning1687-527310.1155/2021/4244040https://doaj.org/article/a8167e7c4ee64b5785d00ee332a31e252021-01-01T00:00:00Zhttp://dx.doi.org/10.1155/2021/4244040https://doaj.org/toc/1687-5273Artificial Intelligence has been widely applied today, and the subsequent privacy leakage problems have also been paid attention to. Attacks such as model inference attacks on deep neural networks can easily extract user information from neural networks. Therefore, it is necessary to protect privacy in deep learning. Differential privacy, as a popular topic in privacy-preserving in recent years, which provides rigorous privacy guarantee, can also be used to preserve privacy in deep learning. Although many articles have proposed different methods to combine differential privacy and deep learning, there are no comprehensive papers to analyze and compare the differences and connections between these technologies. For this purpose, this paper is proposed to compare different differential private methods in deep learning. We comparatively analyze and classify several deep learning models under differential privacy. Meanwhile, we also pay attention to the application of differential privacy in Generative Adversarial Networks (GANs), comparing and analyzing these models. Finally, we summarize the application of differential privacy in deep neural networks.Zhidong ShenTing ZhongHindawi LimitedarticleComputer applications to medicine. Medical informaticsR858-859.7Neurosciences. Biological psychiatry. NeuropsychiatryRC321-571ENComputational Intelligence and Neuroscience, Vol 2021 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Computer applications to medicine. Medical informatics R858-859.7 Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
spellingShingle	Computer applications to medicine. Medical informatics R858-859.7 Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571 Zhidong Shen Ting Zhong Analysis of Application Examples of Differential Privacy in Deep Learning
description	Artificial Intelligence has been widely applied today, and the subsequent privacy leakage problems have also been paid attention to. Attacks such as model inference attacks on deep neural networks can easily extract user information from neural networks. Therefore, it is necessary to protect privacy in deep learning. Differential privacy, as a popular topic in privacy-preserving in recent years, which provides rigorous privacy guarantee, can also be used to preserve privacy in deep learning. Although many articles have proposed different methods to combine differential privacy and deep learning, there are no comprehensive papers to analyze and compare the differences and connections between these technologies. For this purpose, this paper is proposed to compare different differential private methods in deep learning. We comparatively analyze and classify several deep learning models under differential privacy. Meanwhile, we also pay attention to the application of differential privacy in Generative Adversarial Networks (GANs), comparing and analyzing these models. Finally, we summarize the application of differential privacy in deep neural networks.
format	article
author	Zhidong Shen Ting Zhong
author_facet	Zhidong Shen Ting Zhong
author_sort	Zhidong Shen
title	Analysis of Application Examples of Differential Privacy in Deep Learning
title_short	Analysis of Application Examples of Differential Privacy in Deep Learning
title_full	Analysis of Application Examples of Differential Privacy in Deep Learning
title_fullStr	Analysis of Application Examples of Differential Privacy in Deep Learning
title_full_unstemmed	Analysis of Application Examples of Differential Privacy in Deep Learning
title_sort	analysis of application examples of differential privacy in deep learning
publisher	Hindawi Limited
publishDate	2021
url	https://doaj.org/article/a8167e7c4ee64b5785d00ee332a31e25
work_keys_str_mv	AT zhidongshen analysisofapplicationexamplesofdifferentialprivacyindeeplearning AT tingzhong analysisofapplicationexamplesofdifferentialprivacyindeeplearning
_version_	1718443029169176576

Analysis of Application Examples of Differential Privacy in Deep Learning

Ejemplares similares